High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	courty.	delive.	electro	facade	kicker	meadow	office	pipes	playgr.	relief	relief.	terrace	terrai.

DELS-MVS		98.19 56	98.77 62	97.52 55	98.29 65	99.71 16	99.12 44	94.58 66	98.80 125	95.38 56	96.24 140	98.24 78	97.92 133	99.06 43	99.52 1	99.82 17	99.79 46
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
DeepC-MVS	97.63 4	98.33 51	98.57 65	98.04 43	98.62 60	99.65 24	99.45 29	98.15 26	99.51 18	92.80 122	95.74 155	96.44 96	99.46 24	99.37 21	99.50 2	99.78 36	99.81 36
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	96.92 7	98.67 40	99.05 48	98.23 39	99.57 29	99.45 75	99.11 45	94.66 61	99.69 5	96.80 35	96.55 131	99.61 56	99.40 28	98.87 61	99.49 3	99.85 10	99.66 135

MSLP-MVS++		99.15 20	99.24 38	99.04 17	99.52 35	99.49 66	99.09 47	98.07 32	99.37 34	98.47 11	97.79 87	99.89 38	99.50 16	98.93 53	99.45 4	99.61 152	99.76 68

IS_MVSNet		97.86 62	98.86 58	96.68 82	96.02 108	99.72 13	98.35 85	93.37 95	98.75 137	94.01 89	96.88 118	98.40 75	98.48 112	99.09 40	99.42 5	99.83 15	99.80 38

MVSMamba_PlusPlus		98.20 55	99.31 33	96.90 77	95.83 118	99.65 24	98.96 56	94.33 72	99.46 22	93.04 115	98.73 57	98.88 68	99.47 22	99.13 39	99.41 6	99.78 36	99.89 13

Vis-MVSNet (Re-imp)		97.40 78	98.89 57	95.66 135	95.99 111	99.62 36	97.82 112	93.22 113	98.82 122	91.40 151	96.94 115	98.56 73	95.70 204	99.14 37	99.41 6	99.79 33	99.75 76

PHI-MVS		99.08 24	99.43 22	98.67 30	99.15 48	99.59 48	99.11 45	97.35 42	99.14 78	97.30 30	99.44 15	99.96 12	99.32 35	98.89 58	99.39 8	99.79 33	99.58 153

APD-MVS		99.25 14	99.38 25	99.09 13	99.69 9	99.58 51	99.56 21	98.32 9	98.85 115	97.87 22	98.91 46	99.92 30	99.30 38	99.45 17	99.38 9	99.79 33	99.58 153
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DeepPCF-MVS	97.74 3	98.34 50	99.46 15	97.04 68	98.82 55	99.33 117	96.28 185	97.47 41	99.58 10	94.70 74	98.99 39	99.85 43	97.24 156	99.55 10	99.34 10	97.73 243	99.56 160

MGCNet		98.81 35	99.44 19	98.08 41	98.83 54	99.75 9	99.58 20	95.53 49	99.76 1	96.48 41	99.70 4	98.64 70	98.21 120	99.00 49	99.33 11	99.82 17	99.90 7

DeepC-MVS_fast	98.34 1	99.17 19	99.45 16	98.85 26	99.55 32	99.37 104	99.64 10	98.05 34	99.53 15	96.58 37	98.93 44	99.92 30	99.49 19	99.46 16	99.32 12	99.80 32	99.64 142
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SMA-MVS		99.38 8	99.60 3	99.12 11	99.76 2	99.62 36	99.39 33	98.23 21	99.52 17	98.03 20	99.45 14	99.98 2	99.64 5	99.58 8	99.30 13	99.68 117	99.76 68
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
3Dnovator+	96.92 7	98.71 39	99.05 48	98.32 35	99.53 33	99.34 112	99.06 49	94.61 62	99.65 7	97.49 27	96.75 119	99.86 41	99.44 26	98.78 67	99.30 13	99.81 25	99.67 131

QAPM		98.62 43	99.04 51	98.13 40	99.57 29	99.48 67	99.17 41	94.78 58	99.57 11	96.16 43	96.73 120	99.80 46	99.33 33	98.79 65	99.29 15	99.75 50	99.64 142

EC-MVSNet		98.22 54	99.44 19	96.79 78	95.62 140	99.56 54	99.01 53	92.22 130	99.17 66	94.51 79	99.41 16	99.62 55	99.49 19	99.16 36	99.26 16	99.91 2	99.94 1

APDe-MVS		99.49 3	99.64 1	99.32 4	99.74 4	99.74 12	99.75 3	98.34 5	99.56 12	98.72 9	99.57 10	99.97 8	99.53 15	99.65 2	99.25 17	99.84 12	99.77 61
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.30 11	99.54 9	99.03 18	99.66 18	99.64 30	99.68 6	98.25 17	99.56 12	97.12 33	99.19 24	99.95 17	99.72 1	99.43 18	99.25 17	99.72 84	99.77 61

HFP-MVS		99.32 10	99.53 11	99.07 15	99.69 9	99.59 48	99.63 14	98.31 10	99.56 12	97.37 29	99.27 22	99.97 8	99.70 3	99.35 24	99.24 19	99.71 95	99.76 68

UA-Net		97.13 93	99.14 42	94.78 144	97.21 83	99.38 98	97.56 134	92.04 133	98.48 152	88.03 169	98.39 72	99.91 34	94.03 235	99.33 26	99.23 20	99.81 25	99.25 192

LS3D		97.79 63	98.25 76	97.26 63	98.40 63	99.63 33	99.53 22	98.63 1	99.25 54	88.13 168	96.93 116	94.14 128	99.19 43	99.14 37	99.23 20	99.69 109	99.42 179

X-MVS		98.93 31	99.37 26	98.42 33	99.67 15	99.62 36	99.60 18	98.15 26	99.08 89	93.81 95	98.46 69	99.95 17	99.59 9	99.49 14	99.21 22	99.68 117	99.75 76

PGM-MVS		98.86 33	99.35 30	98.29 36	99.77 1	99.63 33	99.67 7	95.63 48	98.66 142	95.27 63	99.11 31	99.82 45	99.67 4	99.33 26	99.19 23	99.73 71	99.74 85

SteuartSystems-ACMMP		99.20 17	99.51 13	98.83 28	99.66 18	99.66 23	99.71 5	98.12 30	99.14 78	96.62 36	99.16 26	99.98 2	99.12 52	99.63 3	99.19 23	99.78 36	99.83 30
Skip Steuart: Steuart Systems R&D Blog.
test1111		97.09 95	96.83 158	97.39 57	96.92 91	99.81 3	98.44 77	94.45 68	99.17 66	95.85 47	92.10 206	88.97 186	98.78 86	99.02 46	99.11 25	99.88 4	99.63 146

test2506		97.16 91	96.68 163	97.73 49	96.95 89	99.79 4	98.48 73	94.42 69	99.17 66	97.74 25	99.15 27	80.93 249	98.89 73	99.03 44	99.09 26	99.88 4	99.62 148

ECVR-MVS		97.27 84	97.09 141	97.48 56	96.95 89	99.79 4	98.48 73	94.42 69	99.17 66	96.28 42	93.54 189	89.39 182	98.89 73	99.03 44	99.09 26	99.88 4	99.61 151

CS-MVS		98.56 46	99.32 31	97.68 50	98.28 66	99.89 2	98.71 66	94.53 67	99.41 29	95.43 53	99.05 38	98.66 69	99.19 43	99.21 31	99.07 28	99.93 1	99.94 1

TSAR-MVS + MP.		99.27 12	99.57 6	98.92 24	98.78 57	99.53 58	99.72 4	98.11 31	99.73 3	97.43 28	99.15 27	99.96 12	99.59 9	99.73 1	99.07 28	99.88 4	99.82 31
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
aaEdge-Enhanced		99.51 1	99.57 6	99.44 1	99.71 7	99.65 24	99.83 1	98.29 13	99.50 20	99.61 2	99.69 5	99.94 26	99.50 16	99.50 13	99.06 30	99.71 95	99.64 142

SD-MVS		99.25 14	99.50 14	98.96 22	98.79 56	99.55 56	99.33 36	98.29 13	99.75 2	97.96 21	99.15 27	99.95 17	99.61 6	99.17 34	99.06 30	99.81 25	99.84 26
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
sasdasda		97.31 80	97.81 101	96.72 79	96.20 105	99.45 75	98.21 92	91.60 142	99.22 58	95.39 54	98.48 65	90.95 163	99.16 49	97.66 158	99.05 32	99.76 44	99.90 7

DVP-MVS		99.45 4	99.54 9	99.35 3	99.72 6	99.76 6	99.63 14	98.37 2	99.63 9	99.03 6	98.95 43	99.98 2	99.60 7	99.60 7	99.05 32	99.74 57	99.79 46
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
MSP-MVS		99.34 9	99.52 12	99.14 9	99.68 14	99.75 9	99.64 10	98.31 10	99.44 26	98.10 16	99.28 21	99.98 2	99.30 38	99.34 25	99.05 32	99.81 25	99.79 46
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
canonicalmvs		97.31 80	97.81 101	96.72 79	96.20 105	99.45 75	98.21 92	91.60 142	99.22 58	95.39 54	98.48 65	90.95 163	99.16 49	97.66 158	99.05 32	99.76 44	99.90 7

OpenMVS	96.23 11	97.95 61	98.45 70	97.35 58	99.52 35	99.42 92	98.91 58	94.61 62	98.87 112	92.24 140	94.61 178	99.05 67	99.10 54	98.64 79	99.05 32	99.74 57	99.51 171

MGCFI-Net		97.26 86	97.79 104	96.64 86	96.17 107	99.43 87	98.14 99	91.52 147	99.23 55	95.16 66	98.48 65	90.87 165	99.07 57	97.59 164	99.02 37	99.76 44	99.91 6

Vis-MVSNet		96.16 146	98.22 80	93.75 165	95.33 166	99.70 18	97.27 148	90.85 159	98.30 168	85.51 189	95.72 157	96.45 94	93.69 241	98.70 76	99.00 38	99.84 12	99.69 121
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		98.46 47	99.16 41	97.64 52	98.48 62	99.64 30	99.35 35	94.71 60	99.53 15	95.17 65	97.63 94	99.59 57	98.38 117	98.88 60	98.99 39	99.74 57	99.86 22

CDPH-MVS		98.41 48	99.10 44	97.61 53	99.32 45	99.36 106	99.49 25	96.15 47	98.82 122	91.82 147	98.41 70	99.66 54	99.10 54	98.93 53	98.97 40	99.75 50	99.58 153

DPE-MVS		99.39 7	99.55 8	99.20 6	99.63 22	99.71 16	99.66 8	98.33 7	99.29 47	98.40 14	99.64 8	99.98 2	99.31 36	99.56 9	98.96 41	99.85 10	99.70 116
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + ACMM		98.77 36	99.45 16	97.98 45	99.37 40	99.46 71	99.44 31	98.13 29	99.65 7	92.30 136	98.91 46	99.95 17	99.05 58	99.42 19	98.95 42	99.58 171	99.82 31

MED-MVS		99.51 1	99.58 4	99.42 2	99.71 7	99.67 19	99.62 16	98.36 3	99.71 4	99.62 1	99.69 5	99.95 17	99.47 22	99.49 14	98.94 43	99.74 57	99.64 142

EPP-MVSNet		97.75 66	98.71 63	96.63 87	95.68 136	99.56 54	97.51 136	93.10 126	99.22 58	94.99 70	97.18 106	97.30 88	98.65 102	98.83 62	98.93 44	99.84 12	99.92 3

CHOSEN 280x420		97.99 60	99.24 38	96.53 90	98.34 64	99.61 41	98.36 84	89.80 178	99.27 50	95.08 68	99.81 1	98.58 72	98.64 103	99.02 46	98.92 45	98.93 226	99.48 175

CSCG		98.90 32	98.93 56	98.85 26	99.75 3	99.72 13	99.49 25	96.58 45	99.38 32	98.05 19	98.97 41	97.87 81	99.49 19	97.78 149	98.92 45	99.78 36	99.90 7

CHOSEN 1792x2688		96.41 138	96.99 151	95.74 133	98.01 70	99.72 13	97.70 121	90.78 162	99.13 83	90.03 161	87.35 247	95.36 110	98.33 118	98.59 87	98.91 47	99.59 166	99.87 19

MVS_111021_LR		98.67 40	99.41 24	97.81 48	99.37 40	99.53 58	98.51 72	95.52 51	99.27 50	94.85 71	99.56 11	99.69 53	99.04 59	99.36 22	98.88 48	99.60 160	99.58 153

DVP-MVS++		99.41 6	99.64 1	99.14 9	99.69 9	99.75 9	99.64 10	98.33 7	99.67 6	98.10 16	99.66 7	99.99 1	99.33 33	99.62 5	98.86 49	99.74 57	99.90 7

CP-MVS		99.27 12	99.44 19	99.08 14	99.62 24	99.58 51	99.53 22	98.16 24	99.21 61	97.79 23	99.15 27	99.96 12	99.59 9	99.54 11	98.86 49	99.78 36	99.74 85

MAR-MVS		97.71 67	98.04 89	97.32 59	99.35 44	98.91 146	97.65 129	91.68 140	98.00 182	97.01 34	97.72 92	94.83 117	98.85 79	98.44 96	98.86 49	99.41 203	99.52 166
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
SPE-MVS-test		98.58 45	99.42 23	97.60 54	98.52 61	99.91 1	98.60 69	94.60 64	99.37 34	94.62 75	99.40 17	99.16 64	99.39 29	99.36 22	98.85 52	99.90 3	99.92 3

SF-MVS		99.18 18	99.32 31	99.03 18	99.65 20	99.41 95	98.87 59	98.24 20	99.14 78	98.73 8	99.11 31	99.92 30	98.92 67	99.22 30	98.84 53	99.76 44	99.56 160

SED-MVS		99.44 5	99.58 4	99.28 5	99.69 9	99.76 6	99.62 16	98.35 4	99.51 18	99.05 5	99.60 9	99.98 2	99.28 40	99.61 6	98.83 54	99.70 105	99.77 61

MVS_111021_HR		98.59 44	99.36 27	97.68 50	99.42 38	99.61 41	98.14 99	94.81 57	99.31 44	95.00 69	99.51 12	99.79 48	99.00 62	98.94 52	98.83 54	99.69 109	99.57 159

CNLPA		99.03 29	99.05 48	99.01 21	99.27 46	99.22 131	99.03 51	97.98 35	99.34 42	99.00 7	98.25 76	99.71 52	99.31 36	98.80 64	98.82 56	99.48 192	99.17 197

FMVSNet2		96.64 129	97.50 114	95.63 136	93.81 186	97.98 198	98.09 102	90.87 158	98.99 101	93.48 105	93.17 197	95.25 112	97.89 134	98.63 80	98.80 57	99.68 117	99.67 131

MP-MVS		99.07 25	99.36 27	98.74 29	99.63 22	99.57 53	99.66 8	98.25 17	99.00 100	95.62 49	98.97 41	99.94 26	99.54 14	99.51 12	98.79 58	99.71 95	99.73 96
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ETV-MVS		98.05 58	99.25 37	96.65 84	95.61 141	99.61 41	98.26 91	93.52 89	98.90 111	93.74 100	99.32 20	99.20 62	98.90 70	99.21 31	98.72 59	99.87 8	99.79 46

TSAR-MVS + GP.		98.66 42	99.36 27	97.85 47	97.16 85	99.46 71	99.03 51	94.59 65	99.09 86	97.19 32	99.73 3	99.95 17	99.39 29	98.95 51	98.69 60	99.75 50	99.65 138

ACMMP_NAP		99.05 27	99.45 16	98.58 32	99.73 5	99.60 46	99.64 10	98.28 16	99.23 55	94.57 76	99.35 19	99.97 8	99.55 13	99.63 3	98.66 61	99.70 105	99.74 85

OMC-MVS		98.84 34	99.01 53	98.65 31	99.39 39	99.23 130	99.22 38	96.70 44	99.40 30	97.77 24	97.89 86	99.80 46	99.21 41	99.02 46	98.65 62	99.57 175	99.07 204

FMVSNet3		97.02 98	98.12 85	95.73 134	93.59 192	97.98 198	98.34 86	91.32 151	98.80 125	93.92 91	97.21 101	95.94 106	97.63 144	98.61 82	98.62 63	99.61 152	99.65 138

CNVR-MVS		99.23 16	99.28 35	99.17 7	99.65 20	99.34 112	99.46 28	98.21 22	99.28 48	98.47 11	98.89 48	99.94 26	99.50 16	99.42 19	98.61 64	99.73 71	99.52 166

baseline		97.45 76	98.70 64	95.99 128	95.89 113	99.36 106	98.29 87	91.37 150	99.21 61	92.99 117	98.40 71	96.87 93	97.96 132	98.60 85	98.60 65	99.42 202	99.86 22

Casviewmamba		97.31 80	97.93 96	96.58 89	95.74 126	99.47 70	98.19 94	93.31 103	99.17 66	93.45 107	96.43 135	93.34 139	98.98 63	98.82 63	98.55 66	99.82 17	99.75 76

MVS_Test		97.30 83	98.54 66	95.87 130	95.74 126	99.28 122	98.19 94	91.40 149	99.18 65	91.59 149	98.17 78	96.18 101	98.63 104	98.61 82	98.55 66	99.66 131	99.78 54

EPNet		98.05 58	98.86 58	97.10 66	99.02 51	99.43 87	98.47 75	94.73 59	99.05 95	95.62 49	98.93 44	97.62 85	95.48 212	98.59 87	98.55 66	99.29 213	99.84 26
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CVMVSNet		95.33 164	97.09 141	93.27 180	95.23 167	98.39 186	95.49 199	92.58 129	97.71 198	83.00 208	94.44 182	93.28 140	93.92 238	97.79 148	98.54 69	99.41 203	99.45 177

casdiffmvs		96.93 104	97.43 123	96.34 101	95.70 131	99.50 65	97.75 118	93.22 113	98.98 102	92.64 124	94.97 173	91.71 157	98.93 66	98.62 81	98.52 70	99.82 17	99.72 110
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewdifsd2359ckpt07		97.07 96	97.81 101	96.22 108	95.75 125	99.42 92	98.19 94	93.27 108	99.14 78	91.92 145	95.46 164	93.66 133	98.53 110	98.75 71	98.48 71	99.65 136	99.73 96

PVSNet_Blended_VisFu		97.41 77	98.49 69	96.15 117	97.49 75	99.76 6	96.02 190	93.75 85	99.26 52	93.38 108	93.73 187	99.35 60	96.47 178	98.96 50	98.46 72	99.77 42	99.90 7

casdiffmvs_mvg		97.27 84	97.97 94	96.46 95	95.83 118	99.51 64	98.42 78	93.32 100	98.34 166	92.38 134	95.64 158	95.35 111	98.91 68	98.73 74	98.45 73	99.86 9	99.80 38
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DCV-MVSNet		97.56 72	98.36 72	96.62 88	96.44 96	98.36 188	98.37 82	91.73 139	99.11 84	94.80 72	98.36 73	96.28 99	98.60 106	98.12 115	98.44 74	99.76 44	99.87 19

baseline1		97.58 71	98.05 87	97.02 71	96.21 104	99.45 75	97.71 120	93.71 87	98.47 153	95.75 48	98.78 52	93.20 142	98.91 68	98.52 91	98.44 74	99.81 25	99.53 163

NCCC		99.05 27	99.08 45	99.02 20	99.62 24	99.38 98	99.43 32	98.21 22	99.36 38	97.66 26	97.79 87	99.90 36	99.45 25	99.17 34	98.43 76	99.77 42	99.51 171

hybridcas		97.23 87	97.70 110	96.69 81	95.70 131	99.48 67	98.27 90	93.27 108	99.23 55	94.08 88	95.30 168	92.92 143	98.98 63	98.79 65	98.41 77	99.83 15	99.75 76

PVSNet_BlendedMVS		97.51 74	97.71 105	97.28 61	98.06 68	99.61 41	97.31 146	95.02 55	99.08 89	95.51 51	98.05 80	90.11 174	98.07 127	98.91 56	98.40 78	99.72 84	99.78 54

PVSNet_Blended		97.51 74	97.71 105	97.28 61	98.06 68	99.61 41	97.31 146	95.02 55	99.08 89	95.51 51	98.05 80	90.11 174	98.07 127	98.91 56	98.40 78	99.72 84	99.78 54

train_agg		98.73 38	99.11 43	98.28 37	99.36 42	99.35 109	99.48 27	97.96 36	98.83 120	93.86 94	98.70 59	99.86 41	99.44 26	99.08 42	98.38 80	99.61 152	99.58 153

CDS-MVSNet		96.59 133	98.02 91	94.92 143	94.45 179	98.96 144	97.46 138	91.75 138	97.86 191	90.07 160	96.02 144	97.25 89	96.21 182	98.04 129	98.38 80	99.60 160	99.65 138
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HPM-MVS++		99.10 23	99.30 34	98.86 25	99.69 9	99.48 67	99.59 19	98.34 5	99.26 52	96.55 39	99.10 33	99.96 12	99.36 31	99.25 29	98.37 82	99.64 142	99.66 135

MCST-MVS		99.11 22	99.27 36	98.93 23	99.67 15	99.33 117	99.51 24	98.31 10	99.28 48	96.57 38	99.10 33	99.90 36	99.71 2	99.19 33	98.35 83	99.82 17	99.71 113

MSDG		98.27 53	98.29 74	98.24 38	99.20 47	99.22 131	99.20 39	97.82 38	99.37 34	94.43 82	95.90 148	97.31 87	99.12 52	98.76 69	98.35 83	99.67 126	99.14 201

test0.0.03 1		96.69 121	98.12 85	95.01 142	95.49 160	98.99 141	95.86 192	90.82 160	98.38 162	92.54 130	96.66 124	97.33 86	95.75 202	97.75 152	98.34 85	99.60 160	99.40 182

GBi-Net		96.98 100	98.00 92	95.78 131	93.81 186	97.98 198	98.09 102	91.32 151	98.80 125	93.92 91	97.21 101	95.94 106	97.89 134	98.07 122	98.34 85	99.68 117	99.67 131

test1		96.98 100	98.00 92	95.78 131	93.81 186	97.98 198	98.09 102	91.32 151	98.80 125	93.92 91	97.21 101	95.94 106	97.89 134	98.07 122	98.34 85	99.68 117	99.67 131

FMVSNet1		95.77 154	96.41 178	95.03 141	93.42 195	97.86 205	97.11 160	89.89 175	98.53 150	92.00 143	89.17 232	93.23 141	98.15 124	98.07 122	98.34 85	99.61 152	99.69 121

E6new		96.66 127	97.04 147	96.21 109	95.52 155	99.46 71	97.65 129	93.22 113	98.40 160	92.26 138	95.22 170	90.02 177	98.89 73	98.06 126	98.30 89	99.74 57	99.79 46

E6		96.66 127	97.04 147	96.21 109	95.52 155	99.46 71	97.65 129	93.22 113	98.40 160	92.26 138	95.22 170	90.02 177	98.89 73	98.06 126	98.30 89	99.74 57	99.79 46

diffmvs_AUTHOR		96.68 123	97.10 140	96.19 115	95.71 129	99.37 104	97.91 108	93.19 120	99.36 38	91.97 144	95.90 148	89.02 185	98.67 101	98.01 132	98.30 89	99.68 117	99.74 85

viewmanbaseed2359cas		96.92 106	97.60 112	96.14 118	95.71 129	99.44 84	97.82 112	93.39 91	98.93 107	91.34 152	96.10 142	92.27 150	98.82 81	98.40 98	98.30 89	99.75 50	99.75 76

EIA-MVS		97.70 68	98.78 61	96.44 96	95.72 128	99.65 24	98.14 99	93.72 86	98.30 168	92.31 135	98.63 60	97.90 80	98.97 65	98.92 55	98.30 89	99.78 36	99.80 38

UGNet		97.66 69	99.07 47	96.01 127	97.19 84	99.65 24	97.09 161	93.39 91	99.35 40	94.40 84	98.79 51	99.59 57	94.24 232	98.04 129	98.29 94	99.73 71	99.80 38
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
E2		97.34 79	98.05 87	96.50 93	95.61 141	99.43 87	97.83 111	93.38 94	99.15 73	93.69 101	97.79 87	93.65 134	98.79 83	98.36 100	98.28 95	99.73 71	99.73 96

viewmacassd2359aftdt		96.50 135	97.01 150	95.91 129	95.65 138	99.45 75	97.65 129	93.31 103	98.36 164	90.30 158	94.48 181	90.82 166	98.77 88	97.91 141	98.26 96	99.76 44	99.77 61

IterMVS-LS		96.12 147	97.48 117	94.53 147	95.19 168	97.56 223	97.15 157	89.19 190	99.08 89	88.23 167	94.97 173	94.73 119	97.84 139	97.86 146	98.26 96	99.60 160	99.88 17
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous202405211			97.40 126		96.45 95	99.54 57	98.08 105	93.79 82	98.24 172		93.55 188	94.41 124	98.88 77	98.04 129	98.24 98	99.75 50	99.76 68

E3new		96.98 100	97.47 120	96.40 98	95.57 149	99.44 84	97.67 125	93.32 100	98.72 138	93.30 109	96.50 132	91.42 161	98.83 80	98.28 105	98.21 99	99.73 71	99.74 85

viewcassd2359sk11		97.19 90	97.82 99	96.44 96	95.59 147	99.43 87	97.70 121	93.35 96	99.15 73	93.50 104	97.20 105	92.68 146	98.77 88	98.38 99	98.21 99	99.73 71	99.73 96

EPNet_dtu		96.30 141	98.53 67	93.70 168	98.97 52	98.24 192	97.36 143	94.23 74	98.85 115	79.18 230	99.19 24	98.47 74	94.09 234	97.89 144	98.21 99	98.39 233	98.85 213
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CPTT-MVS		99.14 21	99.20 40	99.06 16	99.58 28	99.53 58	99.45 29	97.80 39	99.19 64	98.32 15	98.58 62	99.95 17	99.60 7	99.28 28	98.20 102	99.64 142	99.69 121

E4		96.62 131	96.98 153	96.21 109	95.53 152	99.45 75	97.68 123	93.28 107	98.43 155	92.18 142	94.78 177	90.21 173	98.86 78	98.00 133	98.19 103	99.74 57	99.75 76

E3		96.98 100	97.49 115	96.39 99	95.60 144	99.44 84	97.68 123	93.32 100	98.80 125	93.19 111	96.50 132	91.49 159	98.80 82	98.28 105	98.19 103	99.73 71	99.74 85

HyFIR lowres test		95.99 150	96.56 165	95.32 139	97.99 71	99.65 24	96.54 177	88.86 196	98.44 154	89.77 164	84.14 258	97.05 91	99.03 60	98.55 89	98.19 103	99.73 71	99.86 22

diffmvs		96.83 111	97.33 129	96.25 104	95.76 124	99.34 112	98.06 106	93.22 113	99.43 28	92.30 136	96.90 117	89.83 181	98.55 108	98.00 133	98.14 106	99.64 142	99.70 116
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E5new		96.68 123	97.05 145	96.24 105	95.52 155	99.45 75	97.67 125	93.33 98	98.42 157	92.41 132	95.34 166	90.30 171	98.79 83	97.94 137	98.13 107	99.74 57	99.74 85

E5		96.68 123	97.05 145	96.24 105	95.52 155	99.45 75	97.67 125	93.33 98	98.42 157	92.41 132	95.34 166	90.30 171	98.79 83	97.94 137	98.13 107	99.74 57	99.74 85

TAPA-MVS	97.53 5	98.41 48	98.84 60	97.91 46	99.08 50	99.33 117	99.15 42	97.13 43	99.34 42	93.20 110	97.75 90	99.19 63	99.20 42	98.66 77	98.13 107	99.66 131	99.48 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PLC	97.93 2	99.02 30	98.94 55	99.11 12	99.46 37	99.24 127	99.06 49	97.96 36	99.31 44	99.16 4	97.90 85	99.79 48	99.36 31	98.71 75	98.12 110	99.65 136	99.52 166
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
onestephybrid01		96.90 107	97.41 125	96.31 102	95.85 116	99.34 112	97.43 140	93.35 96	99.39 31	93.17 113	95.53 163	92.12 153	98.40 115	97.73 153	98.11 111	99.65 136	99.68 126

DPM-MVS		98.31 52	98.53 67	98.05 42	98.76 58	98.77 154	99.13 43	98.07 32	99.10 85	94.27 87	96.70 122	99.84 44	98.70 95	97.90 143	98.11 111	99.40 205	99.28 188

Anonymous20231211		97.10 94	97.06 144	97.14 65	96.32 98	99.52 61	98.16 97	93.76 83	98.84 119	95.98 45	90.92 214	94.58 123	98.90 70	97.72 155	98.10 113	99.71 95	99.75 76

gg-mvs-nofinetune		90.85 240	94.14 210	87.02 248	94.89 174	99.25 125	98.64 67	76.29 266	88.24 268	57.50 273	79.93 264	95.45 109	95.18 221	98.77 68	98.07 114	99.62 150	99.24 193

viewmamba		96.88 109	97.43 123	96.23 107	95.81 123	99.35 109	97.57 133	93.17 124	99.46 22	92.46 131	96.40 137	91.48 160	98.72 94	97.59 164	98.05 115	99.63 148	99.68 126

CANet_DTU		96.64 129	99.08 45	93.81 163	97.10 86	99.42 92	98.85 60	90.01 171	99.31 44	79.98 226	99.78 2	99.10 66	97.42 152	98.35 101	98.05 115	99.47 194	99.53 163

Fast-Effi-MVS+		95.38 162	96.52 168	94.05 160	94.15 181	99.14 135	97.24 151	86.79 220	98.53 150	87.62 174	94.51 179	87.06 194	98.76 90	98.60 85	98.04 117	99.72 84	99.77 61

viewdifsd2359ckpt13		96.93 104	97.71 105	96.03 125	95.58 148	99.43 87	97.42 141	93.30 106	99.09 86	91.43 150	96.95 114	92.45 147	98.70 95	98.30 104	97.98 118	99.72 84	99.73 96

GG-mvs-BLEND		69.11 263	98.13 84	35.26 267	3.49 283	98.20 194	94.89 212	2.38 277	98.42 157	5.82 284	96.37 138	98.60 71	5.97 279	98.75 71	97.98 118	99.01 223	98.61 224

viewdifsd2359ckpt09		97.00 99	97.68 111	96.21 109	95.54 151	99.40 96	97.73 119	93.31 103	99.17 66	92.24 140	96.62 126	92.71 144	98.76 90	98.19 112	97.95 120	99.66 131	99.71 113

hybrid		96.87 110	97.45 121	96.19 115	95.83 118	99.32 120	97.44 139	93.21 118	99.44 26	92.66 123	97.41 97	90.38 170	98.39 116	97.93 139	97.94 121	99.59 166	99.70 116

hybridnocas07		96.80 113	97.32 130	96.20 114	95.82 121	99.34 112	97.56 134	93.20 119	99.45 24	92.55 129	96.73 120	90.52 168	98.44 113	97.51 169	97.93 122	99.64 142	99.75 76

Effi-MVS+		95.81 153	97.31 134	94.06 159	95.09 169	99.35 109	97.24 151	88.22 207	98.54 149	85.38 190	98.52 63	88.68 187	98.70 95	98.32 102	97.93 122	99.74 57	99.84 26

GeoE		95.98 152	97.24 136	94.51 148	95.02 171	99.38 98	98.02 107	87.86 213	98.37 163	87.86 172	92.99 203	93.54 135	98.56 107	98.61 82	97.92 124	99.73 71	99.85 25

MIMVSNet		94.49 184	97.59 113	90.87 224	91.74 220	98.70 163	94.68 225	78.73 260	97.98 183	83.71 202	97.71 93	94.81 118	96.96 162	97.97 135	97.92 124	99.40 205	98.04 240

DI_MVS_pp		96.90 107	97.49 115	96.21 109	95.61 141	99.40 96	98.72 65	92.11 131	99.14 78	92.98 118	93.08 201	95.14 113	98.13 125	98.05 128	97.91 126	99.74 57	99.73 96

testgi		95.67 156	97.48 117	93.56 171	95.07 170	99.00 138	95.33 203	88.47 204	98.80 125	86.90 179	97.30 99	92.33 149	95.97 191	97.66 158	97.91 126	99.60 160	99.38 184

thres100view900		96.72 119	96.47 173	97.00 74	96.31 99	99.52 61	98.28 88	94.01 76	97.35 204	94.52 77	95.90 148	86.93 197	99.09 56	98.07 122	97.87 128	99.81 25	99.63 146

dtuplus		96.76 115	97.19 137	96.26 103	95.48 162	99.38 98	97.81 114	93.18 123	98.69 140	92.60 126	95.24 169	92.14 152	98.75 92	97.27 181	97.86 129	99.73 71	99.74 85

casdiffseed414692147		96.17 144	96.26 181	96.06 122	95.50 159	99.38 98	97.34 145	93.13 125	98.09 178	91.89 146	93.14 198	87.49 191	98.78 86	98.12 115	97.86 129	99.75 50	99.77 61

viewmambaseed2359dif		96.82 112	97.19 137	96.39 99	95.64 139	99.38 98	98.15 98	93.24 110	98.78 132	92.85 121	95.93 147	91.24 162	98.75 92	97.41 173	97.86 129	99.70 105	99.74 85

COLMAP_ROB	96.15 12	97.78 64	98.17 82	97.32 59	98.84 53	99.45 75	99.28 37	95.43 52	99.48 21	91.80 148	94.83 176	98.36 76	98.90 70	98.09 119	97.85 132	99.68 117	99.15 198
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AdaColmap		99.06 26	98.98 54	99.15 8	99.60 26	99.30 121	99.38 34	98.16 24	99.02 98	98.55 10	98.71 58	99.57 59	99.58 12	99.09 40	97.84 133	99.64 142	99.36 185

thres200		96.76 115	96.53 167	97.03 69	96.31 99	99.67 19	98.37 82	93.99 78	97.68 199	94.49 80	95.83 154	86.77 199	99.18 46	98.26 107	97.82 134	99.82 17	99.66 135

tfpn200view9		96.75 117	96.51 169	97.03 69	96.31 99	99.67 19	98.41 79	93.99 78	97.35 204	94.52 77	95.90 148	86.93 197	99.14 51	98.26 107	97.80 135	99.82 17	99.70 116

thres400		96.71 120	96.45 175	97.02 71	96.28 102	99.63 33	98.41 79	94.00 77	97.82 193	94.42 83	95.74 155	86.26 205	99.18 46	98.20 111	97.79 136	99.81 25	99.70 116

FC-MVSNet-train		97.04 97	97.91 97	96.03 125	96.00 110	98.41 184	96.53 179	93.42 90	99.04 97	93.02 116	98.03 82	94.32 126	97.47 151	97.93 139	97.77 137	99.75 50	99.88 17

baseline2		96.36 140	97.82 99	94.65 146	94.60 178	99.09 136	96.45 181	89.63 180	98.36 164	91.29 154	97.60 95	94.13 129	96.37 179	98.45 94	97.70 138	99.54 184	99.41 180

IterMVS-SCA-FT		94.89 172	97.87 98	91.42 211	94.86 175	97.70 209	97.24 151	84.88 236	98.93 107	75.74 243	94.26 183	98.25 77	96.69 169	98.52 91	97.68 139	99.10 222	99.73 96

viewdifsd2359ckpt11		96.47 136	96.78 159	96.10 121	95.69 133	99.24 127	97.16 155	93.19 120	99.37 34	92.90 120	95.88 152	89.35 183	98.69 98	96.32 208	97.65 140	98.99 224	99.68 126

viewmsd2359difaftdt		96.47 136	96.78 159	96.11 120	95.69 133	99.24 127	97.16 155	93.19 120	99.35 40	92.93 119	95.88 152	89.34 184	98.69 98	96.31 209	97.65 140	98.99 224	99.68 126

thres600view7		96.69 121	96.43 177	97.00 74	96.28 102	99.67 19	98.41 79	93.99 78	97.85 192	94.29 86	95.96 145	85.91 208	99.19 43	98.26 107	97.63 142	99.82 17	99.73 96

PMMVS		97.52 73	98.39 71	96.51 92	95.82 121	98.73 161	97.80 115	93.05 127	98.76 134	94.39 85	99.07 36	97.03 92	98.55 108	98.31 103	97.61 143	99.43 200	99.21 195

IterMVS		94.81 175	97.71 105	91.42 211	94.83 176	97.63 216	97.38 142	85.08 233	98.93 107	75.67 244	94.02 184	97.64 83	96.66 172	98.45 94	97.60 144	98.90 227	99.72 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Effi-MVS+-dtu		95.74 155	98.04 89	93.06 183	93.92 182	99.16 133	97.90 109	88.16 209	99.07 94	82.02 214	98.02 83	94.32 126	96.74 168	98.53 90	97.56 145	99.61 152	99.62 148

gm-plane-assit		89.44 249	92.82 235	85.49 252	91.37 233	95.34 253	79.55 272	82.12 243	91.68 266	64.79 270	87.98 243	80.26 253	95.66 205	98.51 93	97.56 145	99.45 196	98.41 232

LGP-MVS_train		96.23 142	96.89 154	95.46 138	97.32 79	98.77 154	98.81 62	93.60 88	98.58 146	85.52 188	99.08 35	86.67 201	97.83 140	97.87 145	97.51 147	99.69 109	99.73 96

ACMMP		98.74 37	99.03 52	98.40 34	99.36 42	99.64 30	99.20 39	97.75 40	98.82 122	95.24 64	98.85 49	99.87 40	99.17 48	98.74 73	97.50 148	99.71 95	99.76 68
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
CR-MVSNet		94.57 183	97.34 128	91.33 214	94.90 173	98.59 171	97.15 157	79.14 256	97.98 183	80.42 222	96.59 130	93.50 137	96.85 165	98.10 117	97.49 149	99.50 190	99.15 198

PatchT		93.96 192	97.36 127	90.00 235	94.76 177	98.65 166	90.11 254	78.57 261	97.96 186	80.42 222	96.07 143	94.10 130	96.85 165	98.10 117	97.49 149	99.26 215	99.15 198

FC-MVSNet-test		96.07 148	97.94 95	93.89 161	93.60 191	98.67 165	96.62 176	90.30 170	98.76 134	88.62 165	95.57 161	97.63 84	94.48 228	97.97 135	97.48 151	99.71 95	99.52 166

UniMVSNet_ETH3D		93.15 206	92.33 240	94.11 157	93.91 183	98.61 170	94.81 220	90.98 157	97.06 213	87.51 175	82.27 262	76.33 265	97.87 138	94.79 236	97.47 152	99.56 178	99.81 36

PCF-MVS	97.50 6	98.18 57	98.35 73	97.99 44	98.65 59	99.36 106	98.94 57	98.14 28	98.59 145	93.62 102	96.61 127	99.76 51	99.03 60	97.77 150	97.45 153	99.57 175	98.89 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
PatchMatch-RL		97.77 65	98.25 76	97.21 64	99.11 49	99.25 125	97.06 164	94.09 75	98.72 138	95.14 67	98.47 68	96.29 98	98.43 114	98.65 78	97.44 154	99.45 196	98.94 207

TAMVS		95.53 158	96.50 171	94.39 152	93.86 185	99.03 137	96.67 174	89.55 182	97.33 206	90.64 156	93.02 202	91.58 158	96.21 182	97.72 155	97.43 155	99.43 200	99.36 185

LTVRE_ROB	93.20 16	92.84 211	94.92 196	90.43 232	92.83 197	98.63 167	97.08 162	87.87 212	97.91 188	68.42 266	93.54 189	79.46 259	96.62 173	97.55 167	97.40 156	99.74 57	99.92 3
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
MVSTER		97.16 91	97.71 105	96.52 91	95.97 112	98.48 177	98.63 68	92.10 132	98.68 141	95.96 46	99.23 23	91.79 156	96.87 164	98.76 69	97.37 157	99.57 175	99.68 126

Baseline_NR-MVSNet		93.87 194	93.98 217	93.75 165	91.66 222	97.02 238	95.53 198	91.52 147	97.16 212	87.77 173	87.93 245	83.69 224	96.35 180	95.10 232	97.23 158	99.68 117	99.73 96

FMVSNet5		95.42 160	96.47 173	94.20 154	92.26 207	95.99 247	95.66 195	87.15 218	97.87 190	93.46 106	96.68 123	93.79 132	97.52 148	97.10 188	97.21 159	99.11 221	96.62 260

pm-mvs1		94.27 185	95.57 190	92.75 187	92.58 200	98.13 195	94.87 214	90.71 164	96.70 223	83.78 199	89.94 227	89.85 180	94.96 225	97.58 166	97.07 160	99.61 152	99.72 110

dtuonly		94.95 169	96.84 157	92.74 188	93.54 193	98.69 164	97.08 162	89.98 172	97.82 193	78.62 233	92.78 204	94.68 120	98.05 131	97.68 157	97.05 161	99.13 220	99.20 196

Fast-Effi-MVS+-dtu		95.38 162	98.20 81	92.09 197	93.91 183	98.87 148	97.35 144	85.01 235	99.08 89	81.09 218	98.10 79	96.36 97	95.62 207	98.43 97	97.03 162	99.55 180	99.50 173

TransMVSNet (Re)		93.45 200	94.08 213	92.72 189	92.83 197	97.62 219	94.94 210	91.54 146	95.65 241	83.06 207	88.93 235	83.53 229	94.25 231	97.41 173	97.03 162	99.67 126	98.40 235

DU-MVS		93.98 191	94.44 207	93.44 175	91.66 222	97.77 206	95.03 206	91.57 144	97.17 210	86.12 181	93.13 199	81.13 248	96.60 174	95.10 232	97.01 164	99.67 126	99.80 38

TSAR-MVS + COLMAP		96.79 114	96.55 166	97.06 67	97.70 74	98.46 179	99.07 48	96.23 46	99.38 32	91.32 153	98.80 50	85.61 210	98.69 98	97.64 162	96.92 165	99.37 208	99.06 205

CLD-MVS		96.74 118	96.51 169	97.01 73	96.71 93	98.62 168	98.73 64	94.38 71	98.94 105	94.46 81	97.33 98	87.03 195	98.07 127	97.20 184	96.87 166	99.72 84	99.54 162
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
TranMVSNet+NR-MVSNet		93.67 197	94.14 210	93.13 182	91.28 236	97.58 221	95.60 197	91.97 135	97.06 213	84.05 195	90.64 223	82.22 243	96.17 185	94.94 235	96.78 167	99.69 109	99.78 54

RPMNet		94.66 177	97.16 139	91.75 207	94.98 172	98.59 171	97.00 165	78.37 262	97.98 183	83.78 199	96.27 139	94.09 131	96.91 163	97.36 176	96.73 168	99.48 192	99.09 203

UniMVSNet_NR-MVSNet		94.59 181	95.47 191	93.55 172	91.85 217	97.89 204	95.03 206	92.00 134	97.33 206	86.12 181	93.19 196	87.29 193	96.60 174	96.12 214	96.70 169	99.72 84	99.80 38

ET-MVSNet_ETH3D		96.17 144	96.99 151	95.21 140	88.53 252	98.54 174	98.28 88	92.61 128	98.85 115	93.60 103	99.06 37	90.39 169	98.63 104	95.98 220	96.68 170	99.61 152	99.41 180

ACMH	95.42 14	95.27 165	95.96 184	94.45 150	96.83 92	98.78 153	94.72 223	91.67 141	98.95 103	86.82 180	96.42 136	83.67 225	97.00 160	97.48 171	96.68 170	99.69 109	99.76 68
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OPM-MVS		96.22 143	95.85 188	96.65 84	97.75 72	98.54 174	99.00 54	95.53 49	96.88 217	89.88 162	95.95 146	86.46 204	98.07 127	97.65 161	96.63 172	99.67 126	98.83 216
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMP	96.25 10	96.62 131	96.72 161	96.50 93	96.96 88	98.75 158	97.80 115	94.30 73	98.85 115	93.12 114	98.78 52	86.61 202	97.23 157	97.73 153	96.61 173	99.62 150	99.71 113
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
dmvs_re		96.02 149	96.49 172	95.47 137	93.49 194	99.26 124	97.25 150	93.82 81	97.51 201	90.43 157	97.52 96	87.93 189	98.12 126	96.86 192	96.59 174	99.73 71	99.76 68

ACMH+	95.51 13	95.40 161	96.00 182	94.70 145	96.33 97	98.79 151	96.79 169	91.32 151	98.77 133	87.18 176	95.60 160	85.46 211	96.97 161	97.15 185	96.59 174	99.59 166	99.65 138

CP-MVSNet		93.25 204	94.00 216	92.38 192	91.65 224	97.56 223	94.38 232	89.20 189	96.05 235	83.16 206	89.51 229	81.97 244	96.16 186	96.43 202	96.56 176	99.71 95	99.89 13

HQP-MVS		96.37 139	96.58 164	96.13 119	97.31 81	98.44 181	98.45 76	95.22 53	98.86 113	88.58 166	98.33 74	87.00 196	97.67 143	97.23 182	96.56 176	99.56 178	99.62 148

FA-MVS(training)		96.52 134	98.29 74	94.45 150	95.88 115	99.52 61	97.66 128	81.47 244	98.94 105	93.79 98	95.54 162	99.11 65	98.29 119	98.89 58	96.49 178	99.63 148	99.52 166

PS-CasMVS		92.72 216	93.36 228	91.98 201	91.62 226	97.52 225	94.13 236	88.98 194	95.94 238	81.51 217	87.35 247	79.95 256	95.91 192	96.37 204	96.49 178	99.70 105	99.89 13

Anonymous20231206		90.70 244	93.93 218	86.92 249	90.21 244	96.79 241	90.30 253	86.61 224	96.05 235	69.25 263	88.46 239	84.86 217	85.86 261	97.11 187	96.47 180	99.30 212	97.80 245

MVS-HIRNet		92.51 220	95.97 183	88.48 244	93.73 189	98.37 187	90.33 252	75.36 268	98.32 167	77.78 237	89.15 233	94.87 116	95.14 222	97.62 163	96.39 181	98.51 230	97.11 253

DTE-MVSNet		92.42 225	92.85 233	91.91 204	90.87 240	96.97 239	94.53 231	89.81 176	95.86 240	81.59 216	88.83 236	77.88 263	95.01 224	94.34 239	96.35 182	99.64 142	99.73 96

ACMM	96.26 9	96.67 126	96.69 162	96.66 83	97.29 82	98.46 179	96.48 180	95.09 54	99.21 61	93.19 111	98.78 52	86.73 200	98.17 121	97.84 147	96.32 183	99.74 57	99.49 174
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EU-MVSNet		92.80 213	94.76 201	90.51 230	91.88 215	96.74 243	92.48 243	88.69 201	96.21 230	79.00 231	91.51 210	87.82 190	91.83 253	95.87 222	96.27 184	99.21 216	98.92 211

PEN-MVS		92.72 216	93.20 230	92.15 196	91.29 234	97.31 234	94.67 226	89.81 176	96.19 231	81.83 215	88.58 238	79.06 260	95.61 208	95.21 229	96.27 184	99.72 84	99.82 31

TinyColmap		94.00 190	94.35 208	93.60 169	95.89 113	98.26 190	97.49 137	88.82 197	98.56 148	83.21 205	91.28 213	80.48 252	96.68 170	97.34 177	96.26 186	99.53 186	98.24 236

test-mter		94.86 173	97.32 130	92.00 200	92.41 204	98.82 150	96.18 188	86.35 226	98.05 180	82.28 212	96.48 134	94.39 125	95.46 214	98.17 114	96.20 187	99.32 211	99.13 202

NR-MVSNet		94.01 189	94.51 205	93.44 175	92.56 201	97.77 206	95.67 194	91.57 144	97.17 210	85.84 185	93.13 199	80.53 251	95.29 218	97.01 189	96.17 188	99.69 109	99.75 76

tfpnnormal		93.85 196	94.12 212	93.54 173	93.22 196	98.24 192	95.45 200	91.96 136	94.61 244	83.91 197	90.74 220	81.75 246	97.04 159	97.49 170	96.16 189	99.68 117	99.84 26

USDC		94.26 186	94.83 199	93.59 170	96.02 108	98.44 181	97.84 110	88.65 202	98.86 113	82.73 211	94.02 184	80.56 250	96.76 167	97.28 180	96.15 190	99.55 180	98.50 227

thisisatest0530		97.23 87	98.25 76	96.05 123	95.60 144	99.59 48	96.96 166	93.23 111	99.17 66	92.60 126	98.75 55	96.19 100	98.17 121	98.19 112	96.10 191	99.72 84	99.77 61

tttt0517		97.23 87	98.24 79	96.04 124	95.60 144	99.60 46	96.94 167	93.23 111	99.15 73	92.56 128	98.74 56	96.12 103	98.17 121	98.21 110	96.10 191	99.73 71	99.78 54

test-LLR		95.50 159	97.32 130	93.37 177	95.49 160	98.74 159	96.44 182	90.82 160	98.18 173	82.75 209	96.60 128	94.67 121	95.54 210	98.09 119	96.00 193	99.20 217	98.93 208

TESTMET0.1,1		94.95 169	97.32 130	92.20 195	92.62 199	98.74 159	96.44 182	86.67 222	98.18 173	82.75 209	96.60 128	94.67 121	95.54 210	98.09 119	96.00 193	99.20 217	98.93 208

EG-PatchMatch MVS		92.45 221	93.92 219	90.72 229	92.56 201	98.43 183	94.88 213	84.54 238	97.18 209	79.55 228	86.12 255	83.23 236	93.15 246	97.22 183	96.00 193	99.67 126	99.27 191

UniMVSNet (Re)		94.58 182	95.34 192	93.71 167	92.25 208	98.08 196	94.97 208	91.29 156	97.03 215	87.94 170	93.97 186	86.25 206	96.07 187	96.27 211	95.97 196	99.72 84	99.79 46

anonymousdsp		93.12 207	95.86 187	89.93 237	91.09 237	98.25 191	95.12 204	85.08 233	97.44 203	73.30 255	90.89 215	90.78 167	95.25 220	97.91 141	95.96 197	99.71 95	99.82 31

WR-MVS_H		93.54 198	94.67 203	92.22 193	91.95 213	97.91 203	94.58 229	88.75 198	96.64 224	83.88 198	90.66 222	85.13 214	94.40 229	96.54 200	95.91 198	99.73 71	99.89 13

usedtu_dtu_shiyan1		94.86 173	96.31 179	93.16 181	88.71 250	98.02 197	96.17 189	91.31 155	98.43 155	87.18 176	91.68 209	93.37 138	96.06 188	97.46 172	95.83 199	99.53 186	99.40 182

WR-MVS		93.43 202	94.48 206	92.21 194	91.52 229	97.69 211	94.66 227	89.98 172	96.86 218	83.43 203	90.12 224	85.03 215	93.94 237	96.02 218	95.82 200	99.71 95	99.82 31

IB-MVS	93.96 15	95.02 168	96.44 176	93.36 178	97.05 87	99.28 122	90.43 251	93.39 91	98.02 181	96.02 44	94.92 175	92.07 154	83.52 263	95.38 226	95.82 200	99.72 84	99.59 152
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
pmmvs6		91.90 235	92.53 238	91.17 218	91.81 218	97.63 216	93.23 238	88.37 206	93.43 261	80.61 220	77.32 267	87.47 192	94.12 233	96.58 198	95.72 202	98.88 228	99.53 163

MS-PatchMatch		95.99 150	97.26 135	94.51 148	97.46 76	98.76 157	97.27 148	86.97 219	99.09 86	89.83 163	93.51 191	97.78 82	96.18 184	97.53 168	95.71 203	99.35 209	98.41 232

MDTV_nov1_ep13		95.57 157	97.48 117	93.35 179	95.43 163	98.97 143	97.19 154	83.72 242	98.92 110	87.91 171	97.75 90	96.12 103	97.88 137	96.84 194	95.64 204	97.96 239	98.10 239

MIMVSNet1		88.61 250	90.68 252	86.19 251	81.56 266	95.30 254	87.78 264	85.98 229	94.19 248	72.30 261	78.84 265	78.90 261	90.06 254	96.59 197	95.47 205	99.46 195	95.49 262

RPSCF		97.61 70	98.16 83	96.96 76	98.10 67	99.00 138	98.84 61	93.76 83	99.45 24	94.78 73	99.39 18	99.31 61	98.53 110	96.61 196	95.43 206	97.74 241	97.93 244

pmmvs4		95.09 166	95.90 185	94.14 156	92.29 206	97.70 209	95.45 200	90.31 168	98.60 144	90.70 155	93.25 195	89.90 179	96.67 171	97.13 186	95.42 207	99.44 198	99.28 188

GA-MVS		93.93 193	96.31 179	91.16 219	93.61 190	98.79 151	95.39 202	90.69 165	98.25 171	73.28 256	96.15 141	88.42 188	94.39 230	97.76 151	95.35 208	99.58 171	99.45 177

v10		92.79 214	94.06 214	91.31 215	91.78 219	97.29 236	94.87 214	86.10 228	96.97 216	79.82 227	88.16 241	84.56 218	95.63 206	96.33 207	95.31 209	99.65 136	99.80 38

v1192		92.43 224	93.61 223	91.05 220	91.53 228	97.43 229	94.61 228	87.99 211	96.60 225	76.72 239	87.11 250	82.74 241	95.85 196	96.35 206	95.30 210	99.60 160	99.74 85

test_method		87.27 254	91.58 244	82.25 258	75.65 272	87.52 272	86.81 266	72.60 269	97.51 201	73.20 257	85.07 257	79.97 255	88.69 256	97.31 178	95.24 211	96.53 265	98.41 232

v1144		92.81 212	94.03 215	91.40 213	91.68 221	97.60 220	94.73 222	88.40 205	96.71 222	78.48 234	88.14 242	84.46 220	95.45 215	96.31 209	95.22 212	99.65 136	99.76 68

v1240		91.99 234	93.33 229	90.44 231	91.29 234	97.30 235	94.25 234	86.79 220	96.43 228	75.49 246	86.34 254	81.85 245	95.29 218	96.42 203	95.22 212	99.52 188	99.73 96

v144192		92.38 226	93.55 226	91.00 221	91.44 230	97.47 228	94.27 233	87.41 216	96.52 227	78.03 235	87.50 246	82.65 242	95.32 217	95.82 223	95.15 214	99.55 180	99.78 54

v1921920		92.36 228	93.57 224	90.94 222	91.39 232	97.39 231	94.70 224	87.63 215	96.60 225	76.63 240	86.98 251	82.89 239	95.75 202	96.26 212	95.14 215	99.55 180	99.73 96

test20.03		90.65 245	93.71 222	87.09 247	90.44 242	96.24 244	89.74 257	85.46 232	95.59 242	72.99 259	90.68 221	85.33 212	84.41 262	95.94 221	95.10 216	99.52 188	97.06 255

pmmvs5		92.71 218	94.27 209	90.90 223	91.42 231	97.74 208	93.23 238	86.66 223	95.99 237	78.96 232	91.45 211	83.44 234	95.55 209	97.30 179	95.05 217	99.58 171	98.93 208

v7n		91.61 236	92.95 231	90.04 234	90.56 241	97.69 211	93.74 237	85.59 230	95.89 239	76.95 238	86.60 253	78.60 262	93.76 240	97.01 189	94.99 218	99.65 136	99.87 19

v2v482		92.77 215	93.52 227	91.90 205	91.59 227	97.63 216	94.57 230	90.31 168	96.80 221	79.22 229	88.74 237	81.55 247	96.04 190	95.26 228	94.97 219	99.66 131	99.69 121

SCA		94.95 169	97.44 122	92.04 198	95.55 150	99.16 133	96.26 186	79.30 255	99.02 98	85.73 187	98.18 77	97.13 90	97.69 141	96.03 217	94.91 220	97.69 246	97.65 247

v8		92.87 210	93.87 221	91.72 209	92.05 210	97.50 226	94.79 221	88.20 208	96.85 219	80.11 225	90.01 225	82.86 240	95.48 212	95.15 231	94.90 221	99.66 131	99.80 38

V42		93.05 208	93.90 220	92.04 198	91.91 214	97.66 213	94.91 211	89.91 174	96.85 219	80.58 221	89.66 228	83.43 235	95.37 216	95.03 234	94.90 221	99.59 166	99.78 54

SixPastTwentyTwo		93.44 201	95.32 193	91.24 216	92.11 209	98.40 185	92.77 241	88.64 203	98.09 178	77.83 236	93.51 191	85.74 209	96.52 177	96.91 191	94.89 223	99.59 166	99.73 96

tpm		92.38 226	94.79 200	89.56 239	94.30 180	97.50 226	94.24 235	78.97 259	97.72 197	74.93 248	97.97 84	82.91 238	96.60 174	93.65 241	94.81 224	98.33 234	98.98 206

EPMVS		95.05 167	96.86 156	92.94 185	95.84 117	98.96 144	96.68 173	79.87 251	99.05 95	90.15 159	97.12 108	95.99 105	97.49 150	95.17 230	94.75 225	97.59 248	96.96 256

thisisatest0515		94.61 180	96.89 154	91.95 202	92.00 212	98.47 178	92.01 245	90.73 163	98.18 173	83.96 196	94.51 179	95.13 114	93.38 243	97.38 175	94.74 226	99.61 152	99.79 46

v148		92.36 228	92.88 232	91.75 207	91.63 225	97.66 213	92.64 242	90.55 166	96.09 233	83.34 204	88.19 240	80.00 254	92.74 247	93.98 240	94.58 227	99.58 171	99.69 121

TDRefinement		93.04 209	93.57 224	92.41 191	96.58 94	98.77 154	97.78 117	91.96 136	98.12 177	80.84 219	89.13 234	79.87 257	87.78 258	96.44 201	94.50 228	99.54 184	98.15 238

ADS-MVSNet		94.65 178	97.04 147	91.88 206	95.68 136	98.99 141	95.89 191	79.03 258	99.15 73	85.81 186	96.96 113	98.21 79	97.10 158	94.48 238	94.24 229	97.74 241	97.21 252

FE-MVSNET2		87.81 253	88.02 258	87.56 246	80.30 268	96.14 246	90.86 249	87.34 217	93.58 259	74.84 249	71.50 269	65.61 272	92.53 251	96.74 195	94.12 230	99.50 190	98.47 230

PatchmatchNet		94.70 176	97.08 143	91.92 203	95.53 152	98.85 149	95.77 193	79.54 253	98.95 103	85.98 183	98.52 63	96.45 94	97.39 153	95.32 227	94.09 231	97.32 255	97.38 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PM-MVS		89.55 248	90.30 253	88.67 242	87.06 253	95.60 250	90.88 248	84.51 239	96.14 232	75.75 242	86.89 252	63.47 276	94.64 227	96.85 193	93.89 232	99.17 219	99.29 187

FE-MVSNET		86.50 255	88.24 257	84.47 255	76.04 270	94.06 264	87.91 263	86.26 227	92.71 262	69.03 265	77.33 266	66.72 271	88.34 257	95.57 225	93.83 233	99.27 214	97.48 248

pmmvs-eth3d		89.81 247	89.65 255	90.00 235	86.94 254	95.38 252	91.08 246	86.39 225	94.57 245	82.27 213	83.03 261	64.94 273	93.96 236	96.57 199	93.82 234	99.35 209	99.24 193

MDTV_nov1_ep13_2view		92.44 222	95.66 189	88.68 241	91.05 238	97.92 202	92.17 244	79.64 252	98.83 120	76.20 241	91.45 211	93.51 136	95.04 223	95.68 224	93.70 235	97.96 239	98.53 226

new_pmnet		90.45 246	92.84 234	87.66 245	88.96 249	96.16 245	88.71 261	84.66 237	97.56 200	71.91 262	85.60 256	86.58 203	93.28 244	96.07 216	93.54 236	98.46 231	94.39 264

N_pmnet		92.21 231	94.60 204	89.42 240	91.88 215	97.38 232	89.15 260	89.74 179	97.89 189	73.75 253	87.94 244	92.23 151	93.85 239	96.10 215	93.20 237	98.15 238	97.43 250

PatchmatchNet1												92.69 145	93.67 242	96.02 218	93.09 238	98.16 237	97.66 246
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
CostFormer		94.25 187	94.88 198	93.51 174	95.43 163	98.34 189	96.21 187	80.64 248	97.94 187	94.01 89	98.30 75	86.20 207	97.52 148	92.71 244	92.69 239	97.23 258	98.02 242

dtuonlycased		92.09 233	95.05 195	88.64 243	90.98 239	97.03 237	89.54 258	85.55 231	98.13 176	74.33 250	93.51 191	92.03 155	92.59 250	93.63 242	92.52 240	98.85 229	98.50 227

pmmvs3		88.19 251	91.27 245	84.60 254	85.60 256	93.66 265	85.68 267	81.13 246	92.36 264	63.66 272	89.51 229	77.10 264	93.22 245	96.37 204	92.40 241	98.30 235	97.46 249

tpmrst		93.86 195	95.88 186	91.50 210	95.69 133	98.62 168	95.64 196	79.41 254	98.80 125	83.76 201	95.63 159	96.13 102	97.25 155	92.92 243	92.31 242	97.27 256	96.74 257

MDA-MVSNet-bldmvs		87.84 252	89.22 256	86.23 250	81.74 265	96.77 242	83.74 268	89.57 181	94.50 246	72.83 260	96.64 125	64.47 275	92.71 248	81.43 267	92.28 243	96.81 263	98.47 230

Gipuma		81.40 259	81.78 262	80.96 260	83.21 258	85.61 273	79.73 271	76.25 267	97.33 206	64.21 271	55.32 274	55.55 278	86.04 260	92.43 247	92.20 244	96.32 267	93.99 265
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmnet_mix02		92.44 222	94.68 202	89.83 238	92.46 203	97.65 215	89.92 256	90.49 167	98.76 134	73.05 258	91.78 208	90.08 176	94.86 226	94.53 237	91.94 245	98.21 236	98.01 243

ambc			80.99 263		80.04 269	90.84 267	90.91 247		96.09 233	74.18 251	62.81 272	30.59 284	82.44 264	96.25 213	91.77 246	95.91 268	98.56 225

dps		94.63 179	95.31 194	93.84 162	95.53 152	98.71 162	96.54 177	80.12 250	97.81 196	97.21 31	96.98 112	92.37 148	96.34 181	92.46 246	91.77 246	97.26 257	97.08 254

0.4-1-1-0.1		93.46 199	92.78 236	94.25 153	89.58 245	95.89 248	96.90 168	89.00 193	94.50 246	95.29 61	97.21 101	83.62 226	97.58 146	88.01 261	91.72 248	97.15 259	98.48 229

tpm cat1		94.06 188	94.90 197	93.06 183	95.42 165	98.52 176	96.64 175	80.67 247	97.82 193	92.63 125	93.39 194	95.00 115	96.06 188	91.36 250	91.58 249	96.98 261	96.66 259

0.3-1-1-0.015		93.30 203	92.54 237	94.20 154	89.52 247	95.62 249	96.78 170	88.89 195	94.12 249	95.31 57	97.26 100	83.52 230	97.69 141	87.57 263	91.45 250	96.99 260	98.23 237

0.4-1-1-0.2		93.21 205	92.46 239	94.08 158	89.56 246	95.52 251	96.71 171	88.73 199	93.97 257	95.29 61	97.17 107	83.59 227	97.33 154	87.65 262	91.30 251	96.89 262	98.03 241

CMPMVS	70.31 18	90.74 243	91.06 247	90.36 233	97.32 79	97.43 229	92.97 240	87.82 214	93.50 260	75.34 247	83.27 260	84.90 216	92.19 252	92.64 245	91.21 252	96.50 266	94.46 263
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		81.36 260	89.93 254	71.35 263	88.65 251	87.85 271	71.46 274	88.12 210	96.23 229	32.21 279	92.61 205	83.00 237	56.27 273	91.92 249	89.43 253	91.39 272	88.49 268

new-patchmatchnet		86.12 256	87.30 259	84.74 253	86.92 255	95.19 255	83.57 269	84.42 240	92.67 263	65.66 267	80.32 263	64.72 274	89.41 255	92.33 248	89.21 254	98.43 232	96.69 258

PMMVS2		77.26 261	79.47 264	74.70 262	76.00 271	88.37 270	74.22 273	76.34 265	78.31 272	54.13 274	69.96 270	52.50 279	70.14 269	84.83 265	88.71 255	97.35 254	93.58 266

usedtu_dtu_shiyan2		84.24 257	84.83 260	83.55 256	75.12 274	92.45 266	88.33 262	81.21 245	87.18 269	73.36 254	64.78 271	73.58 268	86.68 259	88.73 255	88.30 256	96.59 264	98.82 219

MVE	67.97 19	65.53 266	67.43 271	63.31 266	59.33 276	74.20 274	53.09 279	70.43 270	66.27 275	43.13 275	45.98 278	30.62 283	70.65 268	79.34 269	86.30 257	83.25 276	89.33 267
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
blended_shiyan8		90.91 238	90.97 249	90.84 225	82.45 259	94.62 256	94.96 209	89.15 191	93.94 258	85.03 191	90.85 218	83.58 228	95.78 201	88.79 253	86.19 258	97.70 245	98.80 220

blended_shiyan6		90.91 238	91.00 248	90.80 226	82.44 260	94.60 258	94.86 216	89.05 192	94.08 250	84.93 194	90.75 219	83.74 221	95.81 197	88.79 253	86.19 258	97.71 244	98.83 216

blend_shiyan4		92.70 219	91.74 243	93.81 163	88.98 248	94.51 263	96.29 184	88.71 200	94.00 252	95.31 57	97.12 108	83.52 230	95.91 192	88.20 260	85.99 260	97.69 246	98.84 214

wanda-best-256-512		90.85 240	90.88 250	90.80 226	82.44 260	94.55 259	94.83 217	89.26 185	93.99 253	84.94 192	90.86 216	83.70 222	95.80 198	88.61 256	85.85 261	97.57 249	98.64 222

FE-blended-shiyan7		90.85 240	90.88 250	90.80 226	82.44 260	94.55 259	94.83 217	89.26 185	93.99 253	84.94 192	90.86 216	83.70 222	95.80 198	88.61 256	85.85 261	97.57 249	98.64 222

usedtu_blend_shiyan5		92.28 230	91.78 241	92.86 186	82.44 260	94.55 259	96.69 172	89.26 185	93.99 253	95.31 57	97.12 108	83.52 230	95.91 192	88.61 256	85.85 261	97.57 249	98.84 214

FE-MVSNET3		92.14 232	91.78 241	92.55 190	82.44 260	94.55 259	94.83 217	89.26 185	93.99 253	95.31 57	97.12 108	83.52 230	95.91 192	88.61 256	85.85 261	97.57 249	98.83 216

gbinet_0.2-2-1-0.02		91.19 237	91.20 246	91.18 217	83.37 257	94.62 256	95.06 205	89.43 183	94.06 251	85.87 184	91.99 207	84.54 219	95.79 200	88.81 252	85.62 265	97.56 253	98.74 221

tmp_tt				82.25 258	97.73 73	88.71 269	80.18 270	68.65 271	99.15 73	86.98 178	99.47 13	85.31 213	68.35 270	87.51 264	83.81 266	91.64 270

E-PMN		68.30 264	68.43 268	68.15 264	74.70 275	71.56 276	55.64 277	77.24 263	77.48 274	39.46 276	51.95 277	41.68 282	73.28 267	70.65 270	79.51 267	88.61 274	86.20 271

FPMVS		83.82 258	84.61 261	82.90 257	90.39 243	90.71 268	90.85 250	84.10 241	95.47 243	65.15 268	83.44 259	74.46 266	75.48 265	81.63 266	79.42 268	91.42 271	87.14 269

PMVS	72.60 17	76.39 262	77.66 265	74.92 261	81.04 267	69.37 277	68.47 275	80.54 249	85.39 271	65.07 269	73.52 268	72.91 269	65.67 271	80.35 268	76.81 269	88.71 273	85.25 272
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		68.12 265	68.11 270	68.14 265	75.51 273	71.76 275	55.38 278	77.20 264	77.78 273	37.79 277	53.59 275	43.61 280	74.72 266	67.05 271	76.70 270	88.27 275	86.24 270

VLMVS_CLIP		52.45 269	70.60 267	31.28 270	17.18 279	38.05 280	42.13 281	3.57 276	88.28 267	17.71 282	95.42 165	61.64 277	48.11 275	64.76 272	62.97 271	59.00 277	83.08 273

MVS_clip		53.88 267	72.12 266	32.61 269	20.61 278	45.41 278	36.61 282	4.93 274	91.90 265	24.67 281	89.97 226	74.03 267	57.13 272	61.93 273	58.92 272	51.68 279	82.67 274

VLMVS		52.63 268	68.18 269	34.50 268	22.09 277	38.45 279	42.45 280	4.82 275	85.79 270	35.46 278	89.41 231	67.69 270	49.01 274	57.62 274	58.84 273	53.16 278	79.46 275

testmvs		31.24 270	40.15 273	20.86 271	12.61 280	17.99 281	25.16 283	13.30 272	48.42 277	24.82 280	53.07 276	30.13 285	28.47 276	42.73 275	37.65 274	20.79 280	51.04 277

MVS_baseline		26.32 272	43.96 272	5.74 273	4.07 282	14.12 283	5.93 285	0.00 278	54.17 276	0.00 285	61.72 273	42.95 281	23.20 278	35.99 276	35.87 275	1.21 282	62.88 276

test123		26.75 271	34.25 274	18.01 272	7.93 281	17.18 282	24.85 284	12.36 273	44.83 278	16.52 283	41.80 279	18.10 286	28.29 277	33.08 277	34.79 276	18.10 281	49.95 278

uanet_test		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet-low-res		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

sosnet		0.00 273	0.00 275	0.00 274	0.00 284	0.00 284	0.00 286	0.00 278	0.00 279	0.00 285	0.00 280	0.00 287	0.00 280	0.00 278	0.00 277	0.00 283	0.00 279

ACM-MVS					99.59 27	99.00 138	98.98 55		98.65 143	93.77 99	98.98 40	99.92 30	97.60 145			99.39 207	99.58 153

PatchmatchNet2					92.01 211	97.36 233	89.36 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3										73.82 252	87.22 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
TestfortrainingZip							99.83 1	98.29 13		99.52 3						99.71 95

TPM-MVS					99.57 29	98.90 147	98.79 63			96.52 40	98.62 61	99.91 34	97.56 147			99.44 198	99.28 188
Ray Leroy Khuboni and Hongjun Xu: Textureless Resilient Propagation Matching in Multiple View Stereosis (TPM-MVS). SATNAC 2025
RE-MVS-def										69.05 264

9.14												99.79 48

SR-MVS					99.67 15			98.25 17				99.94 26

our_test_3					92.30 205	97.58 221	90.09 255

MTAPA										98.09 18		99.97 8

MTMP										98.46 13		99.96 12

Patchmatch-RL test							66.86 276

XVS					97.42 77	99.62 36	98.59 70			93.81 95		99.95 17				99.69 109

X-MVStestdata					97.42 77	99.62 36	98.59 70			93.81 95		99.95 17				99.69 109

mPP-MVS					99.53 33							99.89 38

NP-MVS									98.57 147

Patchmtry						98.59 171	97.15 157	79.14 256		80.42 222

DeepMVS_CX						96.85 240	87.43 265	89.27 184	98.30 168	75.55 245	95.05 172	79.47 258	92.62 249	89.48 251		95.18 269	95.96 261

High-resolution multi-view benchmark